Abstract
Abstract: Dealing with the class imbalance issue in the data is a big problem when creating fraud detection systems since valid transactions exceed fraudulent transactions by a large degree. Fraudulent transactions generally make up less than 1% of all transactions. This is a crucial field of research because it can be challenging to discern between a positive instance (a fraudulent case), and it gets tougher when more data are collected and a smaller percentage of such cases are represented. Eight distinct sampling techniques and two classifiers were used in this investigation, and the results of each methodology are reported. The results of this study point to favourable outcomes for sampling methods based on SMOTE. The best F1 score score obtained was with SMOTE sampling strategy on Random Forest classifier at 0.867.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: International Journal for Research in Applied Science and Engineering Technology
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
